Tyler Benster, Julia Gong, Jerry Meng, John Mern, Megumi Sano and Paul Warren will be reviewing Oriol Vinyal's presentation from 2018, focusing on the following three papers:
Learning model-based planning from scratch [2] [John, Tyler]
Imagination-Augmented Agents for Deep Reinforcement Learning [3] [Julia, Meg]
Learning to Search with Monte Carlo Tree Search (MCTS) networks [1] [Jerry, Paul]
These three papers are the assigned readings for class and you might also want to look through Oriol's slides following the link above to get the maximum out of class.
References: